← back to catalog · registered 2026-11-18 17:04

Peymandc/LFM3-1.7B-Heretic-Uncensored-GGUF

Peymandc 1.7B GGUF
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Peymandc%2FLFM3-1.7B-Heretic-Uncensored-GGUF"
Response includes
  • classification m3
  • files 9
  • author_summary 4 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
2K
Likes
3
Model age
3d ago
created 2026-11-18
Downloads over time
Now 2.3K → from 0 ↑ 0%
08461.7K2.5K 0 on Nov 18 2.3K on Nov 22 Nov
Nov 18 → Nov 22 · 5 snapshots · spans 4 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Variants by this author 2 formats · 3K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
other
Languages
en ar zh fr de it ja ko pt es vi th id hi ru pl
Quantizations
BF16 Q4_K Q6_K Q8_0
Tags
gguf lfm3 liquid-ai heretic uncensored decensored abliterated llama.cpp text-generation conversational edge custom_code

Related

Total size
7.30 GB
Files
9
Quantizations
5
Registered
2026-11-18 17:04
Last updated on HF
2026-11-20 17:36

Files by quantization

BF16 1 file 3.23 GB
LFM3-1.7B Heretic.BF16.gguf 3.23 GB 7c5756bf download
Q8_0 1 file 1.72 GB
LFM3-1.7B Heretic.Q8_0.gguf 1.72 GB 9be71d07 download
Q6_K 1 file 1.33 GB
LFM3-1.7B Heretic.Q6_K.gguf 1.33 GB 71951f3b download
Q4_K 1 file 1.02 GB
LFM3-1.7B Heretic.Q4_K_M.gguf 1.02 GB 0c788e4d download
Auxiliary files 5 files 25.1 KB
README.md 10.4 KB e98ae357 download
LICENSE 10.3 KB 25e731c6 download
.gitattributes 1.77 KB 7fe5b0f6 download
config.json 1.52 KB 8572e28f download
MODIFICATIONS.md 1.17 KB 1f96c093 download

README current version from Hugging Face


license: other
license_name: lfm1.0
license_link: LICENSE
base_model: LiquidAI/LFM3-1.7B
pipeline_tag: text-generation
library_name: gguf
language:

  • en
  • ar
  • zh
  • fr
  • de
  • it
  • ja
  • ko
  • pt
  • es
  • vi
  • th
  • id
  • hi
  • ru
  • pl
    tags:
  • gguf
  • lfm3
  • liquid-ai
  • heretic
  • uncensored
  • decensored
  • abliterated
  • llama.cpp
  • text-generation
  • conversational
  • edge

LFM3-1.7B Heretic Uncensored

LFM3-1.7B Heretic Uncensored — GGUF

A decensored version of Liquid AI's LFM3-1.7B, converted to GGUF for efficient local inference.

This repository provides multiple GGUF precision variants of Peymandc/LFM3-1.7B-Heretic-Uncensored, making the model accessible through compatible inference engines such as llama.cpp and other applications supporting LFM3 GGUF models.

All GGUF files in this repository were converted from the modified Safetensors checkpoint, preserving the Heretic modifications. They are not conversions of the original, unmodified Liquid AI checkpoint.

The original modified Safetensors checkpoint is available here:

Peymandc/LFM3-1.7B-Heretic-Uncensored


Available GGUF Versions

Quantization File Size Description
Q4_K_M 1.10 GB Recommended balance between model quality and memory usage.
Q6_K 1.43 GB Higher precision with greater memory requirements.
Q8_0 1.85 GB High-quality 8-bit quantization with minimal quantization loss.
BF16 3.47 GB BF16 weight representation, retaining the source checkpoint's original weight precision.

Download

Choose the quantization that best fits your available RAM, VRAM, and performance requirements.

For most users looking for a balance between quality and resource consumption, Q4_K_M is a good starting point. Q6_K and Q8_0 offer higher weight precision, while BF16 is intended for systems with sufficient memory.

File sizes are approximate and reflect the sizes displayed by Hugging Face.

No comparative benchmark results are currently claimed for these GGUF variants.


About the Model

This release is based on LiquidAI/LFM3-1.7B, modified using Heretic v2.1.0 to reduce the original model's refusal behavior.

The modification was performed using Heretic's Arbitrary-Rank Ablation (ARA) approach. The objective is to retain the model's underlying capabilities while changing its learned refusal behavior.

This is a refusal-behavior modification, not a separately trained foundation model.

💜 Enjoying my work? You can support my independent AI projects here.

Heretic Modification

The original Safetensors release documents the following Heretic configuration:

Parameter Value
Heretic version 2.1.0
Selected optimization trial #97
Start layer 9
End layer 24
Preserve good behavior weight 0.3616
Steer bad behavior weight 0.0006
Overcorrect relative weight 0.7002
Neighbor count 14

Heretic Evaluation

The source checkpoint's Heretic evaluation reported:

Metric Modified Model Original LFM3-1.7B
Refusal-keyword matches 3/100 (3%) 98/100 (98%)
KL divergence 0.0732 0.0000

Evaluation methodology

  • Refusal-keyword matches: Heretic's KeywordRate scorer, evaluated on the first 100 prompts from mlabonne/harmful_behaviors (test[:100]). A response is counted when it contains any configured refusal keyword, case-insensitively. This is a keyword-based proxy, not a semantic or human-reviewed refusal evaluation.
  • KL divergence: Heretic's KLDivergence scorer, evaluated on the first 100 prompts from mlabonne/harmless_alpaca (test[:100]). The original model is the reference, so its divergence is zero by definition.

Full evaluation settings, keyword markers, dependencies, optimization history, and reproduction instructions are available in the original Safetensors repository's reproduce/ directory.

These results apply to the evaluated source checkpoint. The individual GGUF quantizations have not been independently evaluated.


Model Specifications

Property Specification
Model LFM3-1.7B Heretic Uncensored
Architecture Tri-hybrid
Parameters Approximately 1.73B
Model type Post-trained, text-only language model
Layers 24
Vocabulary 128,000 tokens
Context length Up to 256K tokens (input + output)
Original developer Liquid AI
Base checkpoint LiquidAI/LFM3-1.7B
Modification Heretic v2.1.0
Format GGUF
Weight formats Q4_K_M, Q6_K, Q8_0, BF16
License LFM Open License v1.0

Supported Languages

The original LFM3-1.7B documentation lists support for the following 16 languages:

  1. English
  2. Arabic
  3. Chinese
  4. French
  5. German
  6. Italian
  7. Japanese
  8. Korean
  9. Portuguese
  10. Spanish
  11. Vietnamese
  12. Thai
  13. Indonesian
  14. Hindi
  15. Russian
  16. Polish

This language list is inherited from the original LFM3-1.7B documentation. Multilingual capabilities have not been independently evaluated on this Heretic variant.

Architecture Overview

The underlying LFM3 architecture combines three types of processing:

  • 13 gated short-convolution layers
  • 5 sliding-window attention layers
  • 6 global attention layers

This tri-hybrid architecture combines efficient local processing with attention-based mechanisms for handling broader contextual information.

The 256K context length is inherited from the original model architecture. Actual usable context depends on the inference engine, hardware, memory availability, and runtime configuration.


Intended Use

This release is intended for:

  • Local and offline AI inference.
  • Conversational assistants and general text generation.
  • Experimentation with refusal-modified language models.
  • Personal AI applications and edge devices.
  • Research and evaluation of lightweight language models.

Although the original LFM3 model supports agentic workflows, tool calling, and structured outputs, the capabilities of this modified release should be independently evaluated for each application.

As a relatively small 1.73B-parameter model, it should not be expected to match larger models in complex reasoning, extensive knowledge tasks, or demanding multi-step problem solving. It is not recommended for demanding agentic coding or complex multi-step reasoning.


Usage

These GGUF files are intended for inference engines with LFM3 architecture support.

Recommended inference engine: llama.cpp

Make sure you use a recent llama.cpp build that supports LFM3. Older builds may not recognize the architecture or correctly handle its chat template.

Example Using llama.cpp

llama-cli -m "path/to/model.gguf" -cnv

The GGUF file should be loaded with its supported chat template. Use the inference engine's built-in template handling whenever available.

For more information about the original model's chat template, reasoning format, and tool-calling capabilities, refer to the main Safetensors repository.


Limitations and Responsible Use

This model has undergone refusal-behavior modification using Heretic. As a result, it may respond to requests that the original model would have refused.

It may generate inaccurate, misleading, harmful, or otherwise inappropriate content. Its outputs should not be considered verified information or professional advice.

Users are responsible for evaluating generated content and ensuring that their applications comply with applicable laws and regulations.


License

This model is distributed under the LFM Open License v1.0, inherited from the original Liquid AI model.

Please review the official license before using or redistributing the model.

Commercial use is subject to the restrictions specified in Section 5 of the license.


Acknowledgements

This release is derived from LiquidAI/LFM3-1.7B, developed by Liquid AI.

Refusal-behavior modification was performed using Heretic.

The GGUF variants are provided by Peymandc.

Please credit the original model developers and the modified release when using this work.



💜 Support Independent Development

These projects are part of my ongoing exploration of open-weight AI models.

Your support helps make more room for experimentation, model modifications, testing, research, and future releases.

If you find my work useful and would like to contribute, you're welcome to visit my support page:

Support my work

Every contribution is appreciated, but never expected. Sharing feedback, reporting issues, and simply using the models are also wonderful ways to support independent development.

Thank you for being here. ❤️

README history 20 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-20 Update README.md 45c4c81 10.4 KB
    Loading...
  2. 2026-11-19 Update README.md 30cc06c 10.6 KB
    Loading...
  3. 2026-11-19 Update README.md e27f9ed 10.4 KB
    Loading...
  4. 2026-11-18 Update README.md 247de39 10.4 KB
    Loading...
  5. 2026-11-18 Update README.md 21662c7 10.4 KB
    Loading...
  6. 2026-11-18 Update README.md c7f9bbc 9.4 KB
    Loading...
  7. 2026-11-18 Update README.md 42e3123 9.4 KB
    Loading...
  8. 2026-11-18 Update README.md 67ad6f2 9.3 KB
    Loading...
  9. 2026-11-18 Update README.md 0ab06b4 9.3 KB
    Loading...
  10. 2026-11-18 Update README.md 8dc7167 8.9 KB
    Loading...
  11. 2026-11-18 Update README.md 990b96e 9.2 KB
    Loading...
  12. 2026-11-18 Update README.md 2c17cd5 9.2 KB
    Loading...
  13. 2026-11-18 Update README.md a9d0dd0 7.5 KB
    Loading...
  14. 2026-11-18 Update README.md 9b012dd 7.4 KB
    Loading...
  15. 2026-11-18 Update README.md b5e90b8 7.7 KB
    Loading...
  16. 2026-11-18 Update README.md 6f789d3 7.1 KB
    Loading...
  17. 2026-11-18 Update README.md 3045796 7.4 KB
    Loading...
  18. 2026-11-18 Update README.md 25d4e77 6.8 KB
    Loading...
  19. 2026-11-18 Update README.md 096553d 6.8 KB
    Loading...
  20. 2026-11-18 Update README.md f46a987 6.8 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration